Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
Year: 2024
Type: preprint
Abstract: Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed for one specific type of attack and sacrifice significant utility or are soon broken by adaptive attacks. We address these limitations by proposing an information-theoretic defense framework, called Inf2Guard, against the three major types of inference attacks. Our framework, inspired by the success of representation learning, posits that learning shared representations not only saves time/costs but also benefits numerous downstream tasks. Generally, Inf2Guard involves two mutual information objectives, for privacy protection and utility preservation, respectively. Inf2Guard exhibits many merits: it facilitates the design of customized objectives against the specific inference attack; it provides a general defense framework which can treat certain existing defenses as special cases; and importantly, it aids in deriving theoretical results, e.g., inherent utility-privacy tradeoff and guaranteed privacy leakage. Extensive evaluations validate the effectiveness of Inf2Guard for learning privacy-preserving representations against inference attacks and demonstrate the superiority over the baselines.
Source: arXiv (Cornell University)
Institutions: Illinois Institute of Technology, University of Connecticut
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Collaborative Research: SaTC: CORE: Small: Privately Collecting and Analyzing V2X Data for Urban Traffic Modeling, Institute for Data, Econometrics, Algorithms and Learning (IDEAL), CAREER: Privacy Preserving Security Analytics: When Security Meets Privacy, CRII: SaTC: Towards Understanding the Robustness of Graph Neural Networks against Graph Perturbations, Collaborative Research: Data Poisoning Attacks and Infrastructure-Enabled Solutions for Traffic State Estimation and Prediction, IMR: MM-1B: Longitudinal End-device based Performance Measurement of Cellular Networks with Provable Privacy, CAREER: Towards Trustworthy Machine Learning via Learning Trustworthy Representations: An Information-Theoretic Framework
OpenAlex ID: W4392489475